Picture for Amaury Gouverneur

Amaury Gouverneur

Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality

Add code
Oct 21, 2024
Viaarxiv icon

Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems

Add code
Mar 05, 2024
Viaarxiv icon

Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards

Add code
Apr 26, 2023
Viaarxiv icon

An Information-Theoretic Analysis of Bayesian Reinforcement Learning

Add code
Jul 18, 2022
Viaarxiv icon